Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3490 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1453. Min Range: -5.1453
Max Act: 5.1453. Min Act: -0.1700
Data Index: 4069639 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1453. Min Range: -5.1453
Max Act: 5.1140. Min Act: -0.1700
Data Index: 8668162 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1453. Min Range: -5.1453
Max Act: 5.0828. Min Act: -0.1700
Data Index: 7066240 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1453. Min Range: -5.1453
Max Act: 5.0828. Min Act: -0.1700
Data Index: 1449019 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1453. Min Range: -5.1453
Max Act: 5.1140. Min Act: -0.1700
Data Index: 4079543 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1453. Min Range: -5.1453
Max Act: 5.0515. Min Act: -0.1700
Data Index: 496503 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1453. Min Range: -5.1453
Max Act: 5.0203. Min Act: -0.1700
Data Index: 2622993 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1453. Min Range: -5.1453
Max Act: 5.0203. Min Act: -0.1700
Data Index: 6716717 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1453. Min Range: -5.1453
Max Act: 5.0203. Min Act: -0.1700
Data Index: 347106 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1453. Min Range: -5.1453
Max Act: 5.0203. Min Act: -0.1700
Data Index: 3017454 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1453. Min Range: -5.1453
Max Act: 5.0203. Min Act: -0.1700
Data Index: 59785 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1453. Min Range: -5.1453
Max Act: 5.0203. Min Act: -0.1700
Data Index: 6756884 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1453. Min Range: -5.1453
Max Act: 4.9890. Min Act: -0.1700
Data Index: 8444143 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1453. Min Range: -5.1453
Max Act: 4.9578. Min Act: -0.1700
Data Index: 7609072 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1453. Min Range: -5.1453
Max Act: 4.9578. Min Act: -0.1700
Data Index: 4932349 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1453. Min Range: -5.1453
Max Act: 4.9890. Min Act: -0.1700
Data Index: 8589949 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1453. Min Range: -5.1453
Max Act: 4.9890. Min Act: -0.1700
Data Index: 7102250 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1453. Min Range: -5.1453
Max Act: 4.9890. Min Act: -0.1700
Data Index: 6852253 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1453. Min Range: -5.1453
Max Act: 4.9890. Min Act: -0.1700
Data Index: 2566424 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1453. Min Range: -5.1453
Max Act: 4.9265. Min Act: -0.1700
Data Index: 3686010 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19